cover
Contact Name
Iswanto
Contact Email
-
Phone
+628995023004
Journal Mail Official
jrc@umy.ac.id
Editorial Address
Kantor LP3M Gedung D Kampus Terpadu UMY Jl. Brawijaya, Kasihan, Bantul, Yogyakarta 55183
Location
Kab. bantul,
Daerah istimewa yogyakarta
INDONESIA
Journal of Robotics and Control (JRC)
ISSN : 27155056     EISSN : 27155072     DOI : https://doi.org/10.18196/jrc
Journal of Robotics and Control (JRC) is an international open-access journal published by Universitas Muhammadiyah Yogyakarta. The journal invites students, researchers, and engineers to contribute to the development of theoretical and practice-oriented theories of Robotics and Control. Its scope includes (but not limited) to the following: Manipulator Robot, Mobile Robot, Flying Robot, Autonomous Robot, Automation Control, Programmable Logic Controller (PLC), SCADA, DCS, Wonderware, Industrial Robot, Robot Controller, Classical Control, Modern Control, Feedback Control, PID Controller, Fuzzy Logic Controller, State Feedback Controller, Neural Network Control, Linear Control, Optimal Control, Nonlinear Control, Robust Control, Adaptive Control, Geometry Control, Visual Control, Tracking Control, Artificial Intelligence, Power Electronic Control System, Grid Control, DC-DC Converter Control, Embedded Intelligence, Network Control System, Automatic Control and etc.
Articles 23 Documents
Search results for , issue "Vol 5, No 3 (2024)" : 23 Documents clear
Enhancing Humanoid Robot Soccer Ball Tracking, Goal Alignment, and Robot Avoidance Using YOLO-NAS Jati, Handaru; Ilyasa, Nur Alif; Dominic, Dhanapal Durai
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21839

Abstract

This research aims to enhance humanoid robot soccer Ball Tracking, Goal Alignment, and Robot avoidance tasks using YOLO-NAS. The study followed a three-stage approach involving model engineering, which involves model training, code integration, and testing by comparing it with YOLO-v8 and YOLOv7. We measured the mAP (Mean Avegara Precision) and the speed of the detection of each model. Descriptive and Friedman techniques were employed to interpret testing results. In the ball tracking task, YOLO-NAS achieved a success rate of 53.3% compared to YOLOv7 with 68.3%. In the goal alignment task, YOLO-NAS achieved the highest success rate of 91.7%. In the Robot Avoidance task, YOLO-NAS, the same as YOLOv8, 100% nailed the test. These findings suggest that YOLO-NAS performs exceptionally well in the goal-alignment task but does not excel in two other tasks related to humanoid robot soccer.
Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting Sutarna, Nana; Tjahyadi, Christianto; Oktivasari, Prihatin; Dwiyaniti, Murie; Tohazen, Tohazen
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21120

Abstract

Solar energy is one of the most promising renewable energy sources that can reduce greenhouse gas emissions and fossil fuel dependence. However, solar energy production is highly variable and uncertain due to the influence of weather conditions and environmental factors. Accurate forecasting of photovoltaic (PV) power output is essential for optimal planning and operation of PV systems, as well as for integrating them into the power grid. This study develops a deep learning model based on Bidirectional Long Short-Term Memory (Bi-LSTM) to predict short-term PV power output. The main objective is to examine the effect of hyperparameter tuning on the forecasting accuracy and the actual PV output power. The main contribution is identifying the optimal combination of hyperparameters, namely the optimizer, the learning rate, and the activation function, for the PV output. The dataset consists of 143786 observations from sensors measuring solar irradiation, PV surface temperature, ambient temperature, ambient humidity, wind speed, and PV power output for 50 days in Bandung, Indonesia. The data is preprocessed by smoothing and splitting into training (70%, 35 days), validation (15%, 7.5 days), and testing (15%, 7.5 days) sets. The Bi-LSTM model is trained and tested with two optimizers: Adam and RMSprop, and three activation functions: Tanh, ReLU, and Swish, with different learning rates. The results indicate that the optimal performance is obtained by the Bi-LSTM model with Adam optimizer, learning rate of 〖1e〗^(-4), and Tanh activation function. This model has the lowest MAE of 0.002931070979684591, the lowest RMSE of 0.008483537231080387, and the highest R-squared of 0.9988813964105624 when tested with the validation dataset and requires 93 epochs to build. The model also performs well on the test dataset, with the lowest MAE of 0.002717077964916825, the lowest RMSE of 0.007629486798682186, and the highest R-squared of 0.9992563395109665. This study concludes that hyperparameter tuning is a vital step in developing the Bi-LSTM model to improve the accuracy of PV output power prediction.
Improving CBIR Techniques with Deep Learning Approach: An Ensemble Method Using NASNetMobile, DenseNet121, and VGG12 Sadiq, Shereen Saleem
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21805

Abstract

In the evolving field of Content-Based Image Retrieval (CBIR), we introduce a novel approach that integrates deep learning models—NASNetMobile, DenseNet121, and VGG16—with ensemble methods to enhance retrieval accuracy and relevance. This study uniquely combines NASNetMobile's adaptability, DenseNet121's feature extraction, and VGG16's robustness through hard and soft voting techniques, aiming to effectively bridge the semantic gap in CBIR systems. Our comparative analysis against existing CBIR algorithms using diverse online datasets demonstrates superior performance, with our approach achieving up to 98% in accuracy, precision, recall, and F1-score, thereby redefining performance benchmarks. This advancement proves particularly impactful in medical imaging and surveillance, where precise image retrieval is crucial. Our research contributes to CBIR by (1) demonstrating the integrated deep learning ensemble's ability to narrow the semantic gap and (2) providing a comparative performance analysis, underscoring our method's improvement over current technologies. The combination of these models marks a significant step forward in CBIR, offering a more accurate and efficient solution for image retrieval challenges.
Controlling Robots Using Gaze Estimation: A Systematic Bibliometric and Research Trend Analysis Suryadarma, Engelbert Harsandi Erik; Laksono, Pringgo Widyo; Priadythama, Ilham; Herdiman, Lobes
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21686

Abstract

The rapid progression of technology and robotics has brought about a transformative revolution in various fields. From industrial automation to healthcare and beyond, robots have become integral parts of our society, such as using them to move laparoscopic cameras. Eye-gaze-based control in robotics is a cutting-edge innovation, providing enhanced human–robot interaction and control. However, current research is in the underexplored area of gaze-based control for robotics. This paper presents a systematic bibliometric analysis review of controlling robots using gaze estimation. The aim is to provide a research map overview of the use of eye gaze to control robots by clustering application areas based on ISIC-UN and several data acquisition technologies. Over the past 10 years, the number of publications in this field has been relatively stable, averaging 21.5 papers per year, with minimal fluctuations in annual article counts (σ = 4.9). This differs from research on robotics, which grows by an average of 1376 papers per year. Research on using eye gaze for robot control in the last 10 years in the field of human health and social work has only resulted in 17 articles; transportation and storage resulted in 12 articles; professional, scientific, and technical activities resulted in eight articles; information and communication resulted in five articles; and education and art resulted in two articles. Data acquisition technology for eye gaze research, primarily using a commercial eye tracker. Thus, there is significant potential for future research through the utilization of gaze estimation in various fields, as mentioned above.
Enhancing Long-Term Air Temperature Forecasting with Deep Learning Architectures Krivoguz, Denis; Ioshpa, Alexander; Chernyi, Sergei; Zhilenkov, Anton; Kustov, Aleksandr; Zinchenko, Anton; Podelenyuk, Pavel; Tsareva, Polina
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21716

Abstract

Modern challenges in climate prediction necessitate the adoption of advanced deep learning architectures for enhanced precision in temperature forecasting. This study undertakes a comparative evaluation of various neural network designs, particularly focusing on Deep Recurrent Neural Networks (DRNN) and their extension with Gated Recurrent Units (DRNN-GRU), chosen for their proven efficacy in sequential data analysis and long-term dependency capture. Leveraging a comprehensive meteorological dataset, collected from 1961 to 2023, which includes atmospheric temperature, pressure, and precipitation levels, the research unfolds a nuanced understanding of the climate variability. The evaluation framework rigorously applies Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) metrics to quantify model performance. The DRNN and DRNN-GRU architectures are distinguished for their superior predictive accuracy, suggesting their high potential for real-world forecasting applications. These findings are not merely academic; they imply substantial practical implications, particularly for geographic information systems where they can enhance climate monitoring and resource management. The paper culminates with recommendations for dataset expansion and diversified analytical techniques, which are critical for refining the predictive prowess of these models. This research thereby sets a benchmark for future explorations in the field and directs towards innovative avenues to augment the scientific understanding of climate dynamics.
Robust Adaptive Tracking Control for Uncertain Five-Bar Parallel Robot Using Fuzzy CMAC in Order to Improve Accuracy Ngo, Thanh Quyen; Tran, Thanh Hai; Le, Tong Tan Hoa
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21742

Abstract

Parallel robot systems are increasingly important and widely applied due to their superior advantages such as high speed and accuracy. To improve the accuracy of these systems, recent research has focused on developing advanced control methods. However, this remains a significant challenge due to the complex mathematical model of parallel robots. This study introduces a control system based on a fuzzy cerebellar model articulation controller (FCMAC) to control parallel robots. The proposed control system includes FCMAC as the main tracking controller used to estimate the ideal control. A robust controller is employed to compensate for the error between FCMAC and the ideal controller. The parameters of FCMAC are adjusted online based on adaptive laws derived from Lyapunov functions. Finally, a five-bar parallel robot is selected to experiment with the FCMAC algorithm to demonstrate the effectiveness of the proposed controller. The results show that the accuracy of FCMAC is better than that of other algorithms.
Enhancing Harmonic Reduction in Multilevel Inverters using the Weevil Damage Optimization Algorithm Bektaş, Enes; Aldabbagh, Mohammed M; Ahmed, Saadaldeen Rashid; Hussain, Abadal-Salam T.; Taha, Taha A.; Ahmed, Omer K; Ezzat, Sarah B.; Hashim, Abdulghafor Mohammed
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21544

Abstract

In this study, we investigate the efficacy of the newly developed Weevil Damage Optimization Algorithm (WDOA) for addressing harmonic distortion in multilevel inverters. Specifically, harmonics of the fifth and seventh orders are targeted for elimination in a seven-level cascaded multilevel inverter, while harmonics of the fifth, seventh, eleventh, and thirteenth orders are addressed in an eleven-level cascaded multilevel inverter. Through simulation studies encompassing different modulation index values, we demonstrate the effectiveness of the WDOA optimization algorithm in selectively removing harmonics and reducing overall harmonic distortion. While the results showcase promising outcomes, further quantitative metrics and comparative analysis are warranted to fully evaluate the algorithm's performance and its potential implications for practical applications in multilevel inverter systems.
Enhancing Multi-Robot Systems Cooperation through Machine Learning-based Anomaly Detection in Target Pursuit Khatib, Amine; Hamed, Oussama; Hamlich, Mohamed; Mouchtachi, Ahmed
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.20333

Abstract

Effectively pursuing dynamically moving targets in the domain of multi-robot systems (MRS) poses a significant challenge. This paper proposes an innovative leader-follower strategy within the MRS framework, enabling robots to dynamically adjust their roles based on target proximity. This approach fosters coordination, allowing robots to act cohesively when pursuing diverse targets, from other robots to mobile objects. The centralized architecture of the MRS facilitates wireless communication, enabling robots to share sensor-derived data providing proximity cues rather than precise location information. However, data anomalies arising from sensor errors, transmission glitches, or encoding issues pose challenges, compromising the reliability of target-related information. To mitigate this, the paper introduces an advanced methodology integrating the leader-follower strategy with Discriminant Analysis (DA)-based anomaly detection. This novel approach validates and filters data, enhancing data integrity and supporting decision-making processes. The integration of DA methods within the leader-follower strategy is detailed, emphasizing steps in anomaly detection implementation, showcasing robustness in selecting high-quality information for decision-making in dynamic environments. The research's real-world relevance addresses the problem of the impact of sensor anomalies on the performance and reliability of MRS in dynamic environments. By integrating machine learning-based anomaly detection, this methodology enhances MRS adaptability and robustness, particularly in scenarios requiring precise target tracking and coordination. Numerical experiments and simulations demonstrate the efficacy of the DA-based anomaly detection and collaborative hunting strategy in MRS. This method contributes to improved target tracking, enhanced system coordination, and streamlined pursuit of dynamic targets, affirming its practical applicability in surveillance, search and rescue operations, and industrial automation.
Heart Disease Prediction Using Hybrid Machine Learning: A Brief Review Ahmed, Mohammed; Husien, Idress
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21606

Abstract

Cardiovascular disease is a widespread and potentially fatal condition that requires proactive preventive measures and efficient screening approaches on a global scale. To tackle this issue, recent studies have investigated novel machine-learning frameworks that propose to diagnose and forecast cardiovascular disease by capitalizing on enormous datasets and predictive patterns linked to this condition. The research contribution is a thorough examination and implementation of ensemble learning and other hybrid machine-learning techniques for heart disease prediction. By employing ensemble learning on datasets including The Cleveland heart disease dataset and The IEEE Dataport heart diseases dataset such as age, chest pain type, blood pressure, blood glucose level, ECG in rest, heart rate, and four types of chestpain. To predict heart disease, our methodology integrates numerous machine learning models. By capitalising on the merits of specific algorithms while addressing their drawbacks, this approach yields a predictive model that is more resilient. The findings of our research exhibit encouraging outcomes in the realm of heart disease prediction, attaining enhanced precision and dependability in contrast to discrete algorithms. Through the utilisation of ensemble learning, we successfully discerned predictive patterns that are linked to heart disease, thereby augmenting the capabilities of diagnostics. In summary, the findings of our study emphasise the considerable potential of ensemble techniques within the realm of machine learning for the advancement of cardiac disease prediction. By providing a more dependable method for rapid diagnosis and prognosis of cardiac disease, this strategy has substantial ramifications for healthcare practices.
Model Predictive Control Design under Stochastic Parametric Uncertainties Based on Polynomial Chaos Expansions for F-16 Aircraft Purnawan, Heri; Asfihani, Tahiyatul; Kim, Seungkeun; Subchan, Subchan
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21366

Abstract

Parametric uncertainty in a dynamical system has the potential to undermine the performance of a closed-loop controller designed through classical techniques. This paper presents a novel approach to stochastic model predictive control (SMPC) by employing the polynomial chaos expansion (PCE) method called PCE-based model predictive control (PCE-MPC). This method offers a more robust and efficient solution to tackle parameter uncertainties in dynamic systems. The PCE method is utilized to propagate uncertainties through orthogonal polynomials, and the Galerkin projection approach is employed to compute PCE coefficients via intrusive spectral projection (ISP). In Galerkin projection, the inner product involves an integration term, and the integration values are approximated using the Gauss-Legendre quadrature. This quadrature method precisely integrates the p-th order polynomial using 2p-1 points. The numerical case study focuses on the short-period mode of the F-16 aircraft model. Simulation results demonstrate the robust performance of the proposed method in the presence of parameter uncertainties, with system states converging to the original points for each parameter realization under various initial conditions. Comparison results indicate negligible differences between MPC and PCE-MPC, showcasing nearly identical performance. However, further investigation is warranted in other cases and more complex systems involving parameter uncertainties.

Page 2 of 3 | Total Record : 23